VF Inverse CLP

From user's Wiki!
Revision as of 01:59, 1 June 2012 by Hfernandez (Talk | contribs)

Jump to: navigation, search
Computer inverse of a Vector Field

General Information

  • Type: CLP
  • Category: VectorField
  • Author: Nicolas Duchateau
  • Contributor: Xavi Planes
  • Contact: xavier.planes at upf.edu
  • Description: Compute the inverse of a vector field. This is a gradient descent approach based on the definition of the vector field inverse gradient defined in Arsigny et al. [1].

[1] Arsigny, Commowick, Pennec, Ayache. "A log-euclidean framework for statistics on diffeomorphisms", Proc. MICCAI 2006, LNCS vol. 4190, pp. 924-931. Doi: 10.1007/11866565_113.



Name Type Flag / Index Default value / Channel Description
delta_gradient float delta_grad 0.01 Gradient descent tolerance
Nmax_gradientDescent integer Nmax_it_grad 100 Maximum number of iterations for gradient descent
rho_gradientDescent integer rho_grad 1 Weight factor for gradient descent
N_it_expand integer N_it 0 Number of expanding iterations
sig_decrease_expand float sig_decrease 0 Sigma for the exponential decrease
V_radius_expand integer V_radius 3 Smoothing radius
DSRSSpecified boolean DSRS false DownSample / Resample VF
inputVectorFieldFileName image(fileExtensions=".vtk") index 0 input Input Vector Field
outputVFFileName image (fileExtensions=".vtk") index 1 output Output Vector Field


Inverse applied to a vector field:

Computer inverse of a Vector Field


Source code: C++ Source code and XML description

Go back to Users